Improve surrogate evaluation

[robin-janssen]

Plenty of small improvements:

• new tuning evaluation and new finetuning mode to finetune learning rate and related parameters in longer runs
• optimal hyperparameters determined for four new datasets: primordial, primordial_parametric, cloud, cloud_parametric
• bugfixes

[codecov]

Codecov Report

❌ Patch coverage is 50.30675% with 81 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
codes/tune/optuna_fcts.py	41.90%	61 Missing ⚠️
codes/utils/utils.py	54.54%	10 Missing ⚠️
codes/tune/postgres_fcts.py	80.00%	6 Missing ⚠️
codes/utils/data_utils.py	0.00%	3 Missing ⚠️
codes/surrogates/LatentPolynomial/latent_poly.py	0.00%	1 Missing ⚠️

Files with missing lines	Coverage Δ
...surrogates/AbstractSurrogate/abstract_surrogate.py	61.90% <100.00%> (ø)
...es/surrogates/LatentNeuralODE/latent_neural_ode.py	66.24% <ø> (ø)
codes/surrogates/LatentPolynomial/latent_poly.py	78.07% <0.00%> (ø)
codes/utils/data_utils.py	57.50% <0.00%> (ø)
codes/tune/postgres_fcts.py	81.56% <80.00%> (ø)
codes/utils/utils.py	82.87% <54.54%> (ø)
codes/tune/optuna_fcts.py	60.72% <41.90%> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.